Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant changes or dramatic impacts

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating significant changes or impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    words
    -0.68
     Duty
    -0.67
    ios
    -0.66
    bern
    -0.64
     duty
    -0.63
    Bern
    -0.62
    Disclaimer
    -0.60
     Honour
    -0.59
     wishes
    -0.59
    full
    -0.58
    POSITIVE LOGITS
     dramatically
    3.04
     drastically
    2.91
     radically
    2.56
     markedly
    2.20
     significantly
    2.08
     vastly
    2.07
     sharply
    2.06
     substantially
    1.90
     exponentially
    1.83
     massively
    1.81
    Act Density 0.019%

    No Known Activations